feat: decompose non-answerable unknowns

2026-08-03 09:53:28 +01:00
parent db994d7764
commit 42d4da3496
5 changed files with 477 additions and 12 deletions
@@ -25,6 +25,8 @@ The engine should ask one question about one primary concept at a time.

 **The reconstruction model may suggest a question, but only the graph-backed deterministic pipeline may select the user-facing question.**

+**A node is only questionable if it is independently answerable.**
+
 ## One-question / one-concept rule

 Every user-facing question should:
@@ -72,6 +74,26 @@ For the current scenario, this meant creating child unknowns such as:

 The selector then reaches the first foundational child through prerequisite ordering encoded in the decomposition graph rather than through global scoring changes.

+## Atomicity vs answerability
+
+These are different reasoning properties.
+
+- **Atomicity** asks: does this node describe one investigation or several bundled investigations?
+- **Answerability** asks: even if the wording looks singular, can this node be answered directly without first resolving multiple prerequisite dimensions?
+
+A node can appear atomic in wording but still fail answerability.
+
+Examples include broad evaluation containers such as product validation, customer value, business case, technical feasibility, or commercial justification. These often compress several prerequisite investigations into one conclusion-shaped unknown.
+
+That means atomicity alone is not enough.
+
+The engine now decomposes whenever either of these is true:
+
+- the unknown is not atomic
+- the unknown is not independently answerable
+
+This prevents a broad container node from becoming the selected question target even when its wording looks grammatically singular.
+
 ## UI result

 The long compound question no longer survives as the first follow-up in the tested path.